{"total":69,"rows":[{"id":"2107.09044","title":"Just Train Twice: Improving Group Robustness without Training Group Information","created":"2021-07-19","cited_by_count":523,"area":null},{"id":"2403.19647","title":"Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models","created":"2024-03-28","cited_by_count":435,"area":null},{"id":"2204.02937","title":"Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations","created":"2022-04-06","cited_by_count":381,"area":null},{"id":"2201.00299","title":"Improving Out-of-Distribution Robustness via Selective Augmentation","created":"2022-01-02","cited_by_count":202,"area":null},{"id":"2211.14238","title":"Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time","created":"2022-11-25","cited_by_count":90,"area":null},{"id":"2305.00650","title":"Discover and Cure: Concept-aware Mitigation of Spurious Correlation","created":"2023-05-01","cited_by_count":71,"area":null},{"id":"2312.07577","title":"Benchmarking Distribution Shift in Tabular Data with TableShift","created":"2023-12-10","cited_by_count":66,"area":null},{"id":"2201.09637","title":"DrugOOD: Out-of-Distribution (OOD) Dataset Curator and Benchmark for AI-aided Drug Discovery -- A Focus on Affinity Prediction Problems with Noise Annotations","created":"2022-01-24","cited_by_count":54,"area":null},{"id":"2310.03182","title":"Robust and Interpretable Medical Image Classifiers via Concept Bottleneck Models","created":"2023-10-04","cited_by_count":40,"area":null},{"id":"2110.12459","title":"Non-convex Distributionally Robust Optimization: Non-asymptotic Analysis","created":"2021-10-24","cited_by_count":39,"area":null},{"id":"2306.04949","title":"Robust Learning with Progressive Data Expansion Against Spurious Correlation","created":"2023-06-08","cited_by_count":39,"area":null},{"id":"2507.16795","title":"Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning","created":"2025-07-22","cited_by_count":39,"area":null},{"id":"2504.16109","title":"Representation Learning for Tabular Data: A Comprehensive Survey","created":"2025-04-17","cited_by_count":36,"area":null},{"id":"2207.13048","title":"Domain Adaptation under Open Set Label Shift","created":"2022-07-26","cited_by_count":32,"area":null},{"id":"2302.03020","title":"RLSbench: Domain Adaptation Under Relaxed Label Shift","created":"2023-02-06","cited_by_count":30,"area":null},{"id":"2201.00072","title":"BARACK: Partially Supervised Group Robustness With Guarantees","created":"2021-12-31","cited_by_count":25,"area":null},{"id":"2209.07592","title":"Explicit Tradeoffs between Adversarial and Natural Distributional Robustness","created":"2022-09-15","cited_by_count":20,"area":null},{"id":"2212.13669","title":"Near-Optimal Algorithms for Group Distributionally Robust Optimization and Beyond","created":"2022-12-28","cited_by_count":17,"area":null},{"id":"2203.02128","title":"Distributionally Robust Bayesian Optimization with $\\varphi$-divergences","created":"2022-03-04","cited_by_count":16,"area":null},{"id":"2309.08825","title":"Distributionally Robust Post-hoc Classifiers under Prior Shifts","created":"2023-09-16","cited_by_count":16,"area":null},{"id":"2303.05809","title":"Distributionally Robust Optimization with Probabilistic Group","created":"2023-03-10","cited_by_count":14,"area":null},{"id":"2212.02648","title":"Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases","created":"2022-12-05","cited_by_count":13,"area":null},{"id":"2312.05134","title":"Optimal Multi-Distribution Learning","created":"2023-12-08","cited_by_count":13,"area":null},{"id":"2204.03230","title":"What You See is What You Get: Principled Deep Learning via Distributional Generalization","created":"2022-04-07","cited_by_count":11,"area":null},{"id":"2212.06641","title":"Simplicity Bias Leads to Amplified Performance Disparities","created":"2022-12-13","cited_by_count":11,"area":null},{"id":"2402.09891","title":"Do causal predictors generalize better to new domains?","created":"2024-02-15","cited_by_count":11,"area":null},{"id":"2502.01347","title":"Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization","created":"2025-02-03","cited_by_count":9,"area":null},{"id":"2407.08947","title":"Constructing Concept-based Models to Mitigate Spurious Correlations with Minimal Human Effort","created":"2024-07-12","cited_by_count":7,"area":null},{"id":"2106.04443","title":"Robust Generalization despite Distribution Shift via Minimum Discriminating Information","created":"2021-06-08","cited_by_count":6,"area":null},{"id":"2201.03668","title":"Towards Group Robustness in the presence of Partial Group Labels","created":"2022-01-10","cited_by_count":6,"area":null},{"id":"2204.08572","title":"Expert-Calibrated Learning for Online Optimization with Switching Costs","created":"2022-04-18","cited_by_count":6,"area":null},{"id":"2309.06717","title":"Bias Amplification Enhances Minority Group Performance","created":"2023-09-13","cited_by_count":6,"area":null},{"id":"2310.14652","title":"Invariant Feature Regularization for Fair Face Recognition","created":"2023-10-23","cited_by_count":6,"area":null},{"id":"2109.14875","title":"Adversarial Regression with Doubly Non-negative Weighting Matrices","created":"2021-09-30","cited_by_count":5,"area":null},{"id":"2203.09607","title":"Learning Distributionally Robust Models at Scale via Composite Optimization","created":"2022-03-17","cited_by_count":5,"area":null},{"id":"2211.08722","title":"Learning with Noisy Labels over Imbalanced Subpopulations","created":"2022-11-16","cited_by_count":5,"area":null},{"id":"2308.10103","title":"ASPIRE: Language-Guided Data Augmentation for Improving Robustness Against Spurious Correlations","created":"2023-08-19","cited_by_count":5,"area":null},{"id":"2312.03318","title":"Complementary Benefits of Contrastive Learning and Self-Training Under Distribution Shift","created":"2023-12-06","cited_by_count":5,"area":null},{"id":"2505.21422","title":"When Shift Happens - Confounding Is to Blame","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2212.07026","title":"Improving group robustness under noisy labels using predictive uncertainty","created":"2022-12-14","cited_by_count":4,"area":null},{"id":"2302.09267","title":"Stochastic Approximation Approaches to Group Distributionally Robust Optimization and Beyond","created":"2023-02-18","cited_by_count":4,"area":null},{"id":"2305.00677","title":"Robustified Learning for Online Optimization with Memory Costs","created":"2023-05-01","cited_by_count":4,"area":null},{"id":"2309.02211","title":"Distributionally Robust Learning for Multi-source Unsupervised Domain Adaptation","created":"2023-09-05","cited_by_count":4,"area":null},{"id":"2312.16313","title":"Unraveling the Key Components of OOD Generalization via Diversification","created":"2023-12-26","cited_by_count":4,"area":null},{"id":"2311.03055","title":"DRAUC: An Instance-wise Distributionally Robust AUC Optimization Framework","created":"2023-11-06","cited_by_count":3,"area":null},{"id":"2405.18686","title":"Rejection via Learning Density Ratios","created":"2024-05-29","cited_by_count":3,"area":null},{"id":"2208.03066","title":"Tailoring to the Tails: Risk Measures for Fine-Grained Tail Sensitivity","created":"2022-08-05","cited_by_count":2,"area":null},{"id":"2302.05807","title":"Pushing the Accuracy-Group Robustness Frontier with Introspective Self-play","created":"2023-02-11","cited_by_count":2,"area":null},{"id":"2411.10019","title":"Towards Utilising a Range of Neural Activations for Comprehending Representational Associations","created":"2024-11-15","cited_by_count":2,"area":null},{"id":"2505.03585","title":"Decision Making under Model Misspecification: DRO with Robust Bayesian Ambiguity Sets","created":"2025-05-06","cited_by_count":2,"area":null},{"id":"2509.24005","title":"Does Weak-to-strong Generalization Happen under Spurious Correlations?","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2210.12195","title":"Just Mix Once: Worst-group Generalization by Group Interpolation","created":"2022-10-21","cited_by_count":1,"area":null},{"id":"2305.16308","title":"Rectifying Group Irregularities in Explanations for Distribution Shift","created":"2023-05-25","cited_by_count":1,"area":null},{"id":"2408.09157","title":"On the KL-Divergence-based Robust Satisficing Model","created":"2024-08-17","cited_by_count":1,"area":null},{"id":"2411.01045","title":"Fighting Spurious Correlations in Text Classification via a Causal Learning Perspective","created":"2024-11-01","cited_by_count":1,"area":null},{"id":"2501.14182","title":"Single-weight Model Editing for Post-hoc Spurious Correlation Neutralization","created":"2025-01-24","cited_by_count":1,"area":null},{"id":"2505.05868","title":"Open Set Label Shift with Test Time Out-of-Distribution Reference","created":"2025-05-09","cited_by_count":1,"area":null},{"id":"2604.04518","title":"Reproducibility study on how to find Spurious Correlations, Shortcut Learning, Clever Hans or Group-Distributional non-robustness and how to fix them","created":"2026-04-06","cited_by_count":1,"area":null},{"id":"2605.19557","title":"Density-Ratio Losses for Post-Hoc Learning to Defer","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2208.12625","title":"Take One Gram of Neural Features, Get Enhanced Group Robustness","created":"2022-08-26","cited_by_count":0,"area":null},{"id":"2302.13053","title":"Scalable Neural Network Training over Distributed Graphs","created":"2023-02-25","cited_by_count":0,"area":null},{"id":"2311.00079","title":"Spuriosity Rankings for Free: A Simple Framework for Last Layer Retraining Based on Object Detection","created":"2023-10-31","cited_by_count":0,"area":null},{"id":"2311.02622","title":"Hierarchical Simplicity Bias of Neural Networks","created":"2023-11-05","cited_by_count":0,"area":null},{"id":"2403.09869","title":"Mind the GAP: Improving Robustness to Subpopulation Shifts with Group-Aware Priors","created":"2024-03-14","cited_by_count":0,"area":null},{"id":"2502.16948","title":"Deep Minimax Classifiers for Imbalanced Datasets with a Small Number of Minority Samples","created":"2025-02-24","cited_by_count":0,"area":null},{"id":"2503.12012","title":"Mixed-feature Logistic Regression Robust to Distribution Shifts","created":"2025-03-15","cited_by_count":0,"area":null},{"id":"2507.04788","title":"Machine Learning from Explanations","created":"2025-07-07","cited_by_count":0,"area":null},{"id":"2509.23487","title":"Temporal Generalization: A Reality Check","created":"2025-09-27","cited_by_count":0,"area":null},{"id":"2604.05285","title":"Robust Learning of Heterogeneous Dynamic Systems","created":"2026-04-07","cited_by_count":0,"area":null}],"next_cursor":null}